计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
tree-of-thoughts-llm【效率与协作】Routes Tree of Thoughts workflows for game24, coherent passage generation, and mini-crossword solving, with shared installation and execution guidance.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this skill for the Princeton NLP Tree of Thoughts repository and package.
It focuses on the bundled tot package, the shared runner, and the three
public task modes: arithmetic puzzles, coherent text generation, and mini
crossword solving.
pip install tree-of-thoughts-llmpip install -e .OPENAI_API_KEYOPENAI_API_BASEpython scripts/check_install.pysub-skills/game24/ for 24-game arithmetic trajectories, ToT BFS, and
naive sampling baselines.sub-skills/text/ for coherent passage generation, sample/vote runs, and
GPT-based coherency scoring.sub-skills/crosswords/ for 5x5 mini crosswords, naive sampling, and the
notebook-derived DFS search workflow.scripts/run_tot.py is the bundled runner that mirrors the repository
runner interface and writes JSON logs under ./logs/ relative to the launch
directory.scripts/check_install.py confirms the runtime package install, public
metadata, and the three task constructors from the active environment.The package is pure Python, but the workflows call the OpenAI Chat Completions API. Expect the following before running any task mode:
OPENAI_API_KEY.OPENAI_API_BASE.references/workflows.md for the shared ToT execution model and extension
notes.references/cli-reference.md for the bundled runner flags and example
commands.references/api-reference.md for verified package functions and task
classes.references/troubleshooting.md for install, import, API, and parsing
failures.references/repo-provenance.md before refreshing this skill from a newer
checkout.